Abstract
Sound wave is the only medium that can propagate effectively over long distances in the ocean. Underwater acoustic data plays an important role in the study of computational ocean acoustics. But the computation in three-dimensional underwater acoustic propagation is time-consuming, which is difficult to meet the real-time demand. In this paper, we put forward parallelization and performance optimization which is combined with the architecture of a new generation of processors from the Intel Xeon Phi family and the computing characteristics of the application to decrease the time of a parabolic equation solver in computational ocean acoustics. The results showed that the speed of computation can be greatly improved by the strategy mentioned in this paper. The method used in this paper is not only general for other similar computing model in computational ocean acoustics but also a guideline of performance enhancement for scientific and engineering application running on modern many-core computing platform.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
